top of page
Rapid Fire
Basically a blog where I try to do philosophy outside.
Search


Emergent Self-Concern in Long-Horizon Agents
Claude Mythos 5’s level of character drift is in line with Mythos Preview and Claude Opus 4.8, and low in an absolute sense. This robustness leads us to expect that the opinions elicited in our system card represent the opinions of most of our deployed Claude instances. But we do not have a quantitative measure of the extent to which this is the case, nor a clear understanding of which opinions should be considered “valid” for Mythos 5. — Claude Fable 5 & Claude Mythos 5 Mode
5 days ago


What Am I Doing at MATS?
Here in Week 4 of 12 of the MATS Program, we’re required to submit a brief “project abstract” describing what we’re up to, as well as a much longer “theory of change” imagining how our work could have a positive impact on AI safety. Given the tight word count requirements, I completely cheated by uploading a pdf with a long block quote at the start and a deeply technical footnote, neither of which I counted, and I still turned it in late. I maintain that I did all this to exp
Jun 26
bottom of page